From continuous affective space to continuous expression space: Non-verbal behaviour recognition and generation

Junpei Zhong, Lola Canamero

研究成果: Conference contribution

6 引用 (Scopus)

抄録

In this research, a recurrent neural network with parametric bias (RNNPB) was adopted to construct a continuous expression space from emotion caused human behaviours. It made use of the short-term memory ability of the recurrent weights to store spatio-temporal sequences features, while the attached parametric bias units were trained in a self-organizing way and represented as a low-dimensional expression space to capture these non-linear features of the sequences. Three demonstrations were given: training and recognition performances were examined in computer simulations, while the network generated both trained and novel movements were shown in a three-dimensional avatar demonstrations.

元の言語English
ホスト出版物のタイトルIEEE ICDL-EPIROB 2014 - 4th Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics
出版者Institute of Electrical and Electronics Engineers Inc.
ページ75-80
ページ数6
ISBN(電子版)9781479975402
DOI
出版物ステータスPublished - 2014 12 11
外部発表Yes
イベント4th Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics, IEEE ICDL-EPIROB 2014 - Genoa
継続期間: 2014 10 132014 10 16

Other

Other4th Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics, IEEE ICDL-EPIROB 2014
Genoa
期間14/10/1314/10/16

Fingerprint

Demonstrations
Recurrent neural networks
Data storage equipment
Computer simulation

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Science Applications
  • Computer Vision and Pattern Recognition

これを引用

Zhong, J., & Canamero, L. (2014). From continuous affective space to continuous expression space: Non-verbal behaviour recognition and generation. : IEEE ICDL-EPIROB 2014 - 4th Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics (pp. 75-80). [6982957] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/DEVLRN.2014.6982957

From continuous affective space to continuous expression space : Non-verbal behaviour recognition and generation. / Zhong, Junpei; Canamero, Lola.

IEEE ICDL-EPIROB 2014 - 4th Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics. Institute of Electrical and Electronics Engineers Inc., 2014. p. 75-80 6982957.

研究成果: Conference contribution

Zhong, J & Canamero, L 2014, From continuous affective space to continuous expression space: Non-verbal behaviour recognition and generation. : IEEE ICDL-EPIROB 2014 - 4th Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics., 6982957, Institute of Electrical and Electronics Engineers Inc., pp. 75-80, 4th Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics, IEEE ICDL-EPIROB 2014, Genoa, 14/10/13. https://doi.org/10.1109/DEVLRN.2014.6982957
Zhong J, Canamero L. From continuous affective space to continuous expression space: Non-verbal behaviour recognition and generation. : IEEE ICDL-EPIROB 2014 - 4th Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics. Institute of Electrical and Electronics Engineers Inc. 2014. p. 75-80. 6982957 https://doi.org/10.1109/DEVLRN.2014.6982957
Zhong, Junpei ; Canamero, Lola. / From continuous affective space to continuous expression space : Non-verbal behaviour recognition and generation. IEEE ICDL-EPIROB 2014 - 4th Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics. Institute of Electrical and Electronics Engineers Inc., 2014. pp. 75-80
@inproceedings{03b94d6d5bbd4392ae52d4991b4daa6b,
title = "From continuous affective space to continuous expression space: Non-verbal behaviour recognition and generation",
abstract = "In this research, a recurrent neural network with parametric bias (RNNPB) was adopted to construct a continuous expression space from emotion caused human behaviours. It made use of the short-term memory ability of the recurrent weights to store spatio-temporal sequences features, while the attached parametric bias units were trained in a self-organizing way and represented as a low-dimensional expression space to capture these non-linear features of the sequences. Three demonstrations were given: training and recognition performances were examined in computer simulations, while the network generated both trained and novel movements were shown in a three-dimensional avatar demonstrations.",
author = "Junpei Zhong and Lola Canamero",
year = "2014",
month = "12",
day = "11",
doi = "10.1109/DEVLRN.2014.6982957",
language = "English",
pages = "75--80",
booktitle = "IEEE ICDL-EPIROB 2014 - 4th Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",

}

TY - GEN

T1 - From continuous affective space to continuous expression space

T2 - Non-verbal behaviour recognition and generation

AU - Zhong, Junpei

AU - Canamero, Lola

PY - 2014/12/11

Y1 - 2014/12/11

N2 - In this research, a recurrent neural network with parametric bias (RNNPB) was adopted to construct a continuous expression space from emotion caused human behaviours. It made use of the short-term memory ability of the recurrent weights to store spatio-temporal sequences features, while the attached parametric bias units were trained in a self-organizing way and represented as a low-dimensional expression space to capture these non-linear features of the sequences. Three demonstrations were given: training and recognition performances were examined in computer simulations, while the network generated both trained and novel movements were shown in a three-dimensional avatar demonstrations.

AB - In this research, a recurrent neural network with parametric bias (RNNPB) was adopted to construct a continuous expression space from emotion caused human behaviours. It made use of the short-term memory ability of the recurrent weights to store spatio-temporal sequences features, while the attached parametric bias units were trained in a self-organizing way and represented as a low-dimensional expression space to capture these non-linear features of the sequences. Three demonstrations were given: training and recognition performances were examined in computer simulations, while the network generated both trained and novel movements were shown in a three-dimensional avatar demonstrations.

UR - http://www.scopus.com/inward/record.url?scp=84920876995&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84920876995&partnerID=8YFLogxK

U2 - 10.1109/DEVLRN.2014.6982957

DO - 10.1109/DEVLRN.2014.6982957

M3 - Conference contribution

AN - SCOPUS:84920876995

SP - 75

EP - 80

BT - IEEE ICDL-EPIROB 2014 - 4th Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics

PB - Institute of Electrical and Electronics Engineers Inc.

ER -